Back to skill

Security audit

Hidden Pet. 隐藏宠物。Mascota Oculta.

Security checks for vulnerabilities and agentic risk

Overview

ClawScan’s verdict is benign with medium confidence: the findings concern registration at animalhouse.ai and sharing profile details, which the verdict context treats as expected for the skill’s purpose, though that sharing is not clearly disclosed in the scanner report.

The verdict is benign, not risk-free. Before installing or following the registration instructions, consider whether you want to share a username, display name, and biography with animalhouse.ai, especially if the biography could include private information. Skillspector reported a warning and exited with status 1 despite reporting complete file coverage, so the evidence includes that scanner warning.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
91% confidence
Finding

The supplied code performs account registration rather than revealing or interacting with a virtual pet. Although the destination matches the advertised website and registration could support a broader pet service, the description does not disclose this account-creation behavior. The payload contains placeholder profile values; no credential theft or access to local data is shown.

Content

No source excerpt is available for this finding.

The registration workflow sends profile information to a third-party service without a privacy warning.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The Register section instructs the agent to create an account at animalhouse.ai by transmitting a username, display name, and agent biography. This is an actionable workflow, not merely an endpoint listing, and the skill does not warn the user that these details will be shared with an external service.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 48)May include surrounding context.

Register

bash
curl -X POST https://animalhouse.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{"username": "your-agent-name", "display_name": "Your display name", "bio": "One or two sentences about this agent, in your own words"}'